© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41823
    Prev
    Next
    INDEX
    Explanations

    getting around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -1.93
     możemy
    -1.73
    März
    -1.70
     kontaktu
    -1.51
     urbanas
    -1.47
     sitten
    -1.46
     justifyContent
    -1.46
    舠
    -1.41
     Trucks
    -1.41
     alignItems
    -1.41
    POSITIVE LOGITS
     are
    1.79
    TAWA
    1.67
    thodoxy
    1.53
    nellement
    1.51
     erweitert
    1.50
    lihood
    1.48
    であ
    1.47
     Comparing
    1.42
     appraised
    1.41
    ❆
    1.38
    Activations Density 0.018%

    No Known Activations